@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 9f3974a319
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 04:30 UTC

Fix logging of the vLLM Config (#11143)

Jeremy Arnold committed Dec 12, 2024 at 14:05 UTC 9f3974a31911b551d416bb4d435273409d23f021
1 file changed +1 -1
vllm/engine/llm_engine.py
+1 -1
@@ -248,7 +248,7 @@ class LLMEngine:
248 )
249
250 logger.info(
251 - "Initializing an LLM engine (v%s) with config: %r,"
251 + "Initializing an LLM engine (v%s) with config: %s, "
252 "use_cached_outputs=%s, ",
253 VLLM_VERSION,
254 vllm_config,